FastPropModel¶
-
class
getml.feature_learning.
FastPropModel
(aggregation: List[str] = <factory>, loss_function: str = 'SquareLoss', min_df: int = 30, n_most_frequent: int = 0, num_features: int = 200, num_threads: int = 0, sampling_factor: float = 1.0, silent: bool = True, vocab_size: int = 500)[source]¶ Generates simple features based on propositionalization.
FastPropModel
generates simple and easily interpretable features for relational data and time series. It is based on a propositionalization approach and has been optimized for speed and memory efficiency.FastPropModel
generates a large number of features and selects the most relevant ones based on the pair-wise correlation with the target(s).It is recommended to combine
FastPropModel
with theMapping
andSeasonal
preprocessors, which can drastically improve predictive accuracy.- Args:
aggregation (List[
aggregations
], optional):Mathematical operations used by the automated feature learning algorithm to create new features.
Must be from
aggregations
.loss_function (
loss_functions
, optional):Objective function used by the feature learning algorithm to optimize your features. For regression problems use
SquareLoss
and for classification problems useCrossEntropyLoss
.min_df (int, optional):
num_features (int, optional):
Number of features generated by the feature learning algorithm. Range: [1, \(\infty\)]
n_most_frequent (int, optional):
FastPropModel
can find the N most frequent categories in a categorical column and derive features from them. The parameter determines how many categories should be used. Range: [0, \(\infty\)]num_threads (int, optional):
Number of threads used by the feature learning algorithm. If set to zero or a negative value, the number of threads will be determined automatically by the getML engine. Range: [\(0\), \(\infty\)]
sampling_factor (float, optional):
FastProp uses a bootstrapping procedure (sampling with replacement) to train each of the features. The sampling factor is proportional to the share of the samples randomly drawn from the population table every time Multirel generates a new feature. A lower sampling factor (but still greater than 0.0), will lead to less danger of overfitting, less complex statements and faster training. When set to 1.0, roughly 2,000 samples are drawn from the population table. If the population table contains less than 2,000 samples, it will use standard bagging. When set to 0.0, there will be no sampling at all. Range: [0, \(\infty\)]
silent (bool, optional):
Controls the logging during training.
vocab_size (int, optional):
Determines the maximum number of words that are extracted in total from
getml.data.roles.text
columns. This can be interpreted as the maximum size of the bag of words. Range: [0, \(\infty\)]
Example:
population_placeholder = getml.data.Placeholder("population") order_placeholder = getml.data.Placeholder("order") trans_placeholder = getml.data.Placeholder("trans") population_placeholder.join(order_placeholder, join_key="account_id") population_placeholder.join(trans_placeholder, join_key="account_id", time_stamp="date") feature_selector = getml.predictors.XGBoostClassifier( reg_lambda=500 ) predictor = getml.predictors.XGBoostClassifier( reg_lambda=500 ) agg = getml.feature_learning.aggregations feature_learner = getml.feature_learning.FastPropModel( aggregation=[ agg.Avg, agg.Count, agg.Max, agg.Median, agg.Min, agg.Sum, agg.Var ], num_features=200, loss_function=getml.feature_learning.loss_functions.CrossEntropyLoss ) pipe = getml.pipeline.Pipeline( tags=["dfs"], population=population_placeholder, peripheral=[order_placeholder, trans_placeholder], feature_learners=feature_learner, feature_selectors=feature_selector, predictors=predictor, share_selected_features=0.5 ) pipe.check( population_table=population_train, peripheral_tables={"order": order, "trans": trans} ) pipe = pipe.fit( population_table=population_train, peripheral_tables={"order": order, "trans": trans} ) in_sample = pipe.score( population_table=population_train, peripheral_tables={"order": order, "trans": trans} ) out_of_sample = pipe.score( population_table=population_test, peripheral_tables={"order": order, "trans": trans} )
Methods
validate
([params])Checks both the types and the values of all instance variables and raises an exception if something is off.
Attributes